Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating emotional responses or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensus
    -0.62
     onCancelled
    -0.53
    ため
    -0.50
    hdys
    -0.49
     texas
    -0.49
    response
    -0.49
    Kjelder
    -0.47
     israel
    -0.46
    bres
    -0.45
    ☸
    -0.45
    POSITIVE LOGITS
     quelcon
    0.88
     يتيمه
    0.86
     another
    0.83
     other
    0.80
     تانيه
    0.76
    subplots
    0.75
    Aiheesta
    0.75
    Revenir
    0.72
    tvrt
    0.72
     ďal
    0.71
    Act Density 0.339%

    No Known Activations